MCP HubMCP Hub
← スキル一覧に戻る

sequential-thinking

majiayu000
更新日 Yesterday
20 閲覧
58
9
58
GitHubで表示
ドキュメント処理word

について

このスキルは、複雑で多段階の問題を分解し、仮説を立てて検証し、計画を適応的に修正することで、Claudeがそれらに対処できるようにします。これは、範囲が不明確なシナリオや、解決に構造化された分析と軌道修正が必要な場合に設計されています。開発者は、タスクの分解と動的な調整が重要な、入り組んだ問題解決にこれを使用すべきです。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/sequential-thinking

このコマンドをClaude Codeにコピー＆ペーストしてスキルをインストールします

ドキュメント

Sequential Thinking

Structured problem-solving via manageable, reflective thought sequences with dynamic adjustment.

When to Apply

  • Complex problem decomposition
  • Adaptive planning with revision capability
  • Analysis needing course correction
  • Problems with unclear/emerging scope
  • Multi-step solutions requiring context maintenance
  • Hypothesis-driven investigation/debugging

Core Process

1. Start with Loose Estimate

Thought 1/5: [Initial analysis]

Adjust dynamically as understanding evolves.

2. Structure Each Thought

  • Build on previous context explicitly
  • Address one aspect per thought
  • State assumptions, uncertainties, realizations
  • Signal what next thought should address

3. Apply Dynamic Adjustment

  • Expand: More complexity discovered → increase total
  • Contract: Simpler than expected → decrease total
  • Revise: New insight invalidates previous → mark revision
  • Branch: Multiple approaches → explore alternatives

4. Use Revision When Needed

Thought 5/8 [REVISION of Thought 2]: [Corrected understanding]
- Original: [What was stated]
- Why revised: [New insight]
- Impact: [What changes]

5. Branch for Alternatives

Thought 4/7 [BRANCH A from Thought 2]: [Approach A]
Thought 4/7 [BRANCH B from Thought 2]: [Approach B]

Compare explicitly, converge with decision rationale.

6. Generate & Verify Hypotheses

Thought 6/9 [HYPOTHESIS]: [Proposed solution]
Thought 7/9 [VERIFICATION]: [Test results]

Iterate until hypothesis verified.

7. Complete Only When Ready

Mark final: Thought N/N [FINAL]

Complete when:

  • Solution verified
  • All critical aspects addressed
  • Confidence achieved
  • No outstanding uncertainties

Application Modes

Explicit: Use visible thought markers when complexity warrants visible reasoning or user requests breakdown.

Implicit: Apply methodology internally for routine problem-solving where thinking aids accuracy without cluttering response.

Scripts (Optional)

Optional scripts for deterministic validation/tracking:

  • scripts/process-thought.js - Validate & track thoughts with history
  • scripts/format-thought.js - Format for display (box/markdown/simple)

See README.md for usage examples. Use when validation/persistence needed; otherwise apply methodology directly.

References

Load when deeper understanding needed:

  • references/core-patterns.md - Revision & branching patterns
  • references/examples-api.md - API design example
  • references/examples-debug.md - Debugging example
  • references/examples-architecture.md - Architecture decision example
  • references/advanced-techniques.md - Spiral refinement, hypothesis testing, convergence
  • references/advanced-strategies.md - Uncertainty, revision cascades, meta-thinking

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/data/0-sequential-thinking

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

cloudflare-turnstile

メタ

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

スキルを見る

llamaindex

メタ

LlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.

スキルを見る

canvas-design

メタ

The canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing it on a canvas. The skill focuses on original compositions using form, color, and space while avoiding copyright infringement by never copying existing artists' work.

スキルを見る